© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23100
    Prev
    Next
    INDEX
    Explanations

    multiple sclerosis, hepatitis B, rheumatoid arthritis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¯è®©
    -0.07
    å°ģåŃĺ
    -0.06
    aphael
    -0.06
    é¦Ļ
    -0.06
    ![
    -0.06
    ommy
    -0.06
    å¾Īåı¯èĥ½ä¼ļ
    -0.06
    AsyncResult
    -0.05
    ä¸įèĥ½è®©
    -0.05
    pä
    -0.05
    POSITIVE LOGITS
    rch
    0.08
    zijd
    0.08
    rv
    0.07
    thinkable
    0.07
    мÑı
    0.07
    èķ
    0.07
    steen
    0.07
    ÑĪли
    0.07
    RYPT
    0.07
    åŁł
    0.07
    Activations Density 0.932%

    No Known Activations